Method and apparatus for confining and guiding a radiation ablation treatment field - Patents.com

Abstract

A system (100) and method (700, 800, 900) for target region recommendation and guidance in radiation ablation treatment planning is disclosed. In one example, a computing device (104) receives image data (103) relating to a patient from one or more modalities. The computing device (104) determines a recommended target region for treatment based on the image data (103) and determines one or more corresponding segments of a segment model based on the recommended target region. The computing device (104) displays a segment model identifying the determined segments and receives input data modifying the determined segments. Based on the input data, the computing device (104) updates one or more segments and generates target definition data characterizing the updated segments. The computing device (104) transmits the target definition data to treat the patient.

Description

Technical Field

[0001] [Cross - Reference to Related Applications] This application claims priority to U.S. Provisional Application No. 63 / 250,501, filed September 30, 2021, entitled "METHODS AND APPARATUS FOR RADIOABLATION TREATMENT AREA TARGETING AND GUIDANCE" and U.S. Provisional Application No. 63 / 250,521, filed September 30, 2021, entitled "METHODS AND APPARATUS FOR RADIOABLATION TREATMENT AREA TARGETING AND GUIDANCE". The entire contents of these applications are hereby incorporated by reference.

[0002] Aspects of the present disclosure relate generally to medical diagnostic and treatment systems, and more particularly to providing radio (radio - wave) ablation diagnostic, treatment planning, and delivery systems for treating conditions such as cardiac arrhythmias.

Background Art

[0003] Various techniques can be employed to capture or image a patient's metabolic, electrical, and anatomical information. For example, positron emission tomography (PET) is a metabolic imaging technique that generates tomographic images representing the distribution of positron - emitting isotopes in the body. CT (computed tomography) and MRI (magnetic resonance imaging) are anatomical imaging techniques that generate images using X - rays and magnetic fields, respectively. Images from these exemplary techniques can be combined with each other to generate composite anatomical and functional images. For example, software systems such as Varian Medical Systems, Inc.'s Velocity (trademark) software use an image fusion process that deforms and / or registers images to generate a combined image to combine various types of images. Medical specialists such as electrophysiologists and radiation oncologists rely on these images to identify the target area for treatment.

[0004] For example, in cardiac radiation ablation, medical experts cooperate to diagnose arrhythmia, identify the area to be ablated, prescribe radiation therapy, and create a radiation ablation treatment plan. An electrophysiologist can identify one or more areas or targets in the patient's heart to treat arrhythmia based on the patient's anatomy and electrophysiology. The electrophysiologist can, for example, define the target area for ablation relying on combined PET and cardiac CT images. Once the target area is defined by the electrophysiologist, a radiation oncologist can prescribe radiation therapy, including, for example, the number of fractions of radiation to be delivered, the radiation dose to be delivered to the target area, and the maximum dose to adjacent organs at risk. And a dosimetrist can create a radiation ablation treatment plan based on the prescribed radiation therapy. The radiation oncologist may also review and approve the treatment plan. Further, the electrophysiologist may want to know the position, size, and shape of the defined target area to confirm that the target position defined by the radiation ablation treatment plan is correct.

[0005] To create and optimize a treatment plan, it is essential to appropriately identify and define the target area of the organ of the patient to be treated. For example, if the target area is too large, a target volume including areas not requiring treatment will be defined as a result, while if the target area is too small, a target volume not including the area to be treated may be defined as a result. Therefore, there is room for improvement in the radiation ablation treatment planning system used by medical experts, such as the cardiac radiation ablation treatment system used in cardiac radiation ablation treatment planning. SUMMARY OF THE INVENTION

[0006] According to a first aspect of the present invention, a system according to claim 1 is provided.

[0007] According to a second aspect of the present invention, a method executed by a computer according to claim 16 is provided.

[0008] According to a third aspect of the present invention, there is provided a non-transitory computer-readable medium according to claim 19.

[0009] Disclosed are systems and methods for cardiac radiation ablation treatment and planning. In one aspect, a computing device receives image data regarding a patient. For example, the computing device can receive magnetic resonance (MR) image data, computed tomography (CT) image data, or positron emission tomography (PET) image data from an image scanning system. Based on the received image data, the computing device determines a target region recommended as a treatment target. In one aspect, the computing device can also receive report data regarding the patient. The report data can characterize the patient's medical findings such as the patient's diagnosis result. The computing device can determine a target region recommended as a treatment target based on the image data and the report data.

[0010] Furthermore, the computing device receives an input that identifies a change to the target region recommended as a treatment target. The computing device also determines the presence or absence of one or more rule violations based on the change to the target region recommended as a treatment target. Based on the determination of the presence or absence of one or more rule violations, the computing device provides an indication as to whether the change is acceptable for display. For example, if there are no rule violations, the computing device can update the target region recommended as a treatment target based on the change and provide the updated recommended target region for display. On the other hand, if one or more rule violations are confirmed, the computing device can provide an error message for display.

[0011] In one aspect, the system includes a database and a computing device communicably connected to the database. The computing device is configured to receive image data regarding a patient's organ. Then, the computing device is configured to determine a target region recommended as a treatment target for the organ based on the image data. Further, the computing device is configured to generate recommended target data characterizing the recommended target region of the organ. The computing device is also configured to store the recommended target data in the database.

[0012] In one aspect, the computing device is configured to receive a first input identifying a change to the target region recommended as a treatment target. Then, the computing device is configured to determine whether there is a violation of a first rule based on the change to the target region recommended as a treatment target. Further, the computing device is configured to provide an indication of whether the change is acceptable for display based on the determination of the presence or absence of one or more rule violations.

[0013] In one aspect, the computing device is configured to receive image data regarding a patient. Then, the computing device is configured to determine the scar location of the organ based on the image data. Further, the computing device is configured to determine one of a plurality of segments of a model of the organ based on the scar location. Also, the computing device is configured to display the identified model with the determined segment. For example, the computing device displays the determined segment in one color and the other segments in another color among the plurality of segments. In one aspect, the computing device is configured to display the model with the image data overlaid. In one aspect, the computing device is configured to display the image data with the model overlaid.

[0014] In one aspect, a computing device is configured to receive image data regarding a patient. And the computing device is configured to determine the scar location of an organ based on the image data. Further, the computing device is configured to determine the healthy portion of the organ based on the scar location. Also, the computing device is configured to display a model of an organ with the scar location and the healthy portion identified. For example, the computing device can display the scar location of the organ in one color and the healthy portion of the organ in another color.

[0015] In one aspect, a method executed by a computer includes receiving image data regarding a patient. And the method includes determining a target region recommended as a treatment target based on the received image data. In one aspect, the method includes receiving report data regarding the patient. And the method includes determining a target region recommended as a treatment target based on the image data and the report data.

[0016] Further, the method includes receiving an input specifying a change to the target region recommended as a treatment target. And the method includes determining the presence or absence of one or more rule violations based on the change to the target region recommended as a treatment target. Further, the method includes providing an indication of whether the change is acceptable for display based on the determination of the presence or absence of one or more rule violations.

[0017] In one aspect, the method includes receiving image data regarding a patient's organ. And the method includes determining a target region recommended as a treatment target for the organ based on the image data. Further, the method includes generating recommended target data characterizing the recommended target region of the organ. The method includes including the recommended target data in a database.

[0018] In one aspect, the method includes receiving a first input that identifies a change to a target region recommended for treatment. The method then includes determining whether there is a violation of a first rule based on the change to the target region recommended for treatment. Further, the method includes providing an indication of whether the change is acceptable for display based on a determination of the presence or absence of one or more rule violations.

[0019] In one aspect, a method executed by a computer includes receiving image data regarding a patient. The method then includes determining a scar location of an organ based on the image data. Further, the method includes determining one of a plurality of segments of a model of the organ based on the scar location. The method also includes displaying the identified model with the determined segment. In one aspect, the method includes displaying the model with the image data overlaid. In one aspect, the method includes displaying the image data with the model overlaid.

[0020] In one aspect, a method executed by a computer includes receiving image data regarding a patient. The method includes determining a scar location of an organ based on the image data. Further, the method includes determining a healthy portion of the organ based on the scar location. The method then includes displaying a model of the organ with the scar location and the healthy portion identified.

[0021] In one aspect, a non-transitory computer-readable medium storing instructions that, when executed by at least one processor, cause the at least one processor to perform a process that includes receiving image data regarding a patient. The process then includes determining a target region recommended for treatment based on the received image data. In one aspect, the process includes receiving report data regarding the patient. The process then includes determining a target region recommended for treatment based on the image data and the report data.

[0022] Furthermore, this process includes receiving an input that identifies a change to a target region recommended for treatment. Then, this process includes determining whether there is one or more rule violations based on the change to the target region recommended for treatment. Furthermore, this process includes providing an indication of whether the change is acceptable for display based on the determination of whether there is one or more rule violations.

[0023] In one aspect, a non-transitory computer-readable medium storing instructions that, when executed by at least one processor, cause the at least one processor to perform a process including receiving image data regarding a patient's organ. Then, this process includes determining a target region recommended for treatment of the organ based on the image data. Furthermore, this process includes generating recommended target data characterizing the recommended target region of the organ. Then, this process includes including the recommended target data in a database.

[0024] In one aspect, a non-transitory computer-readable medium storing instructions that, when executed by at least one processor, cause the at least one processor to perform a process including receiving a first input that identifies a change to a target region recommended for treatment. Then, this process includes determining whether there is a violation of a first rule based on the change to the target region recommended for treatment. Furthermore, this process includes providing an indication of whether the change is acceptable for display based on the determination of whether there is one or more rule violations.

[0025] In one aspect, a non-transitory computer-readable medium storing instructions that, when executed by at least one processor, cause the at least one processor to perform a process including receiving image data related to a patient. The process includes determining a scar position of an organ based on the image data. Further, the process includes determining one of a plurality of segments of a model of the organ based on the scar position. The process also includes displaying a model with the identified segment. In one aspect, the process includes displaying the model with the image data overlaid. In one aspect, the process includes displaying the image data with the model overlaid.

[0026] In one aspect, a non-transitory computer-readable medium storing instructions that, when executed by at least one processor, cause the at least one processor to perform a process including receiving image data related to a patient. The process includes determining a scar position of an organ based on the image data. Further, the process includes determining a healthy portion of the organ based on the scar position. The process also includes displaying a model of the organ with the scar position and the healthy portion identified.

[0027] In one aspect, a method executed by a computer includes means for receiving image data related to a patient. The method includes means for determining a target region recommended as a treatment target based on the received image data. In one aspect, the method includes means for receiving report data related to the patient. The method includes means for determining a target region recommended as a treatment target based on the image data and the report data.

[0028] Furthermore, the method includes means for receiving an input specifying a change to a target region recommended for treatment. Then, the method includes means for determining the presence or absence of one or more rule violations based on the change to the target region recommended for treatment. Further, the method includes means for providing an indication of whether the change is acceptable for display based on the determination of the presence or absence of one or more rule violations.

[0029] In one aspect, a method executed by a computer includes means for receiving image data regarding a patient's organ. Then, the method includes means for determining a target region recommended for treatment of the organ based on the image data. Further, the method includes means for generating recommended target data characterizing the recommended target region of the organ. Also, the method includes means for storing the recommended target data in a database.

[0030] In one aspect, a method executed by a computer includes means for receiving a first input specifying a change to a target region recommended for treatment. Then, the method includes means for determining whether there is a violation of a first rule based on the change to the target region recommended for treatment. Further, the method includes means for providing an indication of whether the change is acceptable for display based on the determination of the presence or absence of one or more rule violations.

[0031] In one aspect, a method executed by a computer includes means for receiving image data regarding a patient. Then, the method includes means for determining the scar position of an organ based on the image data. Further, the method includes means for determining one of a plurality of segments of a model of the organ based on the scar position. Also, the method includes means for displaying the identified model with the determined segment. In one aspect, the method includes means for overlaying the image data to display the model. In one aspect, the method includes means for overlaying the model to display the image data.

[0032] In one aspect, a method executed by a computer includes means for receiving image data regarding a patient. And the method includes means for determining a scar position of an organ based on the image data. Further, the method includes means for determining a healthy portion of the organ based on the scar position. Also, the method includes means for providing, for display, a model of the organ with the scar position and the healthy portion identified.

Brief Description of the Drawings

[0033] The features and advantages of the present disclosure will be more particularly disclosed and made apparent by the detailed description of the embodiments described below. The detailed description of the embodiments is to be considered in conjunction with the following drawings, in which like numerals indicate like parts.

Figure 1

Figure 2

Figure 3

Figure 4

Figures 5A-5C

Figures 6A-6E

Figure 7

Figure 8

Figure 9

Best Mode for Carrying Out the Invention

[0034] The description of the preferred embodiments is intended to be understood in connection with the accompanying drawings, which should be regarded as a part of the overall description of the present disclosure. Although various changes and alternative forms are possible in the present disclosure, specific embodiments are illustrated in the figures and described in detail herein. The objects and advantages of the subject matter of the claims will become more apparent from the following detailed description of the embodiments illustrated herein in connection with the accompanying drawings.

[0035] Of course, the present disclosure should not be limited to the specific forms described. Rather, the present disclosure encompasses all modifications, equivalents, and alternatives within the spirit and scope of the illustrated embodiments. Terms such as "connect / connect to", "be connected / connected to", "be connected and operate", "be connected and operate" etc. should be broadly understood to mean connecting devices or components to each other so that they can operate (e.g., communicate) with each other mechanically, electrically, by wire, wirelessly, or otherwise, in the relationship intended by the relevant buses or components.

[0036] Referring to the drawings, FIG. 1 shows a block diagram of a cardiac radiation ablation narrowing system 100, which includes an imaging device 102, a treatment planning computing device 106, one or more target recommendation computing devices 104, and a database 116 communicatively connected via a communication network 118. The imaging device 102 is, for example, a CT scanner, an MR scanner, a PET scanner, an electrophysiological imaging device, an ECG, or an ECG imager. In one embodiment, the imaging device 102 is a PET / CT scanner or a PET / MR scanner. In one embodiment, the imaging device 102 and the treatment planning computing device 106 can be part of a radiation ablation treatment system 126 that enables radiation ablation treatment for a patient. For example, the radiation ablation treatment system 126 enables irradiation of a prescribed dose to one or more treatment areas of the patient.

[0037] Each of the target recommendation computing devices 104 and the treatment planning computing device 106 can be a suitable computing device including hardware suitable for data processing or a combination of hardware and software. For example, both can include one or more processors, one or more field programmable gate arrays (FPGAs), one or more application specific integrated circuits (ASICs), one or more state machines, digital circuits, or other suitable circuits. Further, both devices can transmit data to or receive data from the communication network 118. For example, each of the target recommendation computing devices 104 and the treatment planning computing device 106 can be a server such as a cloud-based server, a computer, a laptop, a mobile device, a workstation, or other suitable computing device.

[0038] As an example, FIG. 2 illustrates a computing device 200 that can be an example of each of a target recommended computing device 104 and a treatment planning computing device 106. The computing device 200 includes one or more processors 201, a working memory 202, one or more input / output (I / O) devices 203, an instruction memory 207, a transceiver 204, one or more communication ports 209, and a display 206, all of which operate connected to one or more data buses 208. The data bus 208 enables communication between each device. The data bus 208 can include a wired or wireless communication channel.

[0039] The processor 201 can include one or more individual processors, each having one or more cores. Each of the individual processors can have the same or different structures. The processor 201 can include one or more central processing units (CPUs), one or more graphics processing units (GPUs), application specific integrated circuits (ASICs), digital signal processors (DSPs), and the like.

[0040] The instruction memory 207 can store instructions that can be accessed (e.g., read) and executed by the processor 201. For example, the instruction memory 207 is a non-transitory computer-readable storage medium such as read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory, removable disk, CD-ROM, any non-volatile memory, or any other suitable memory. The processor 201 can be configured to perform the function or process by executing code that embodies the particular function or process stored in the instruction memory 207. For example, the processor 201 can be configured to execute the code stored in the instruction memory 207 to perform any one or more of the functions, methods, or processes disclosed herein.

[0041] Furthermore, the processor 201 can store data in the working memory 202 and read data from the working memory 202. For example, the processor 201 can store a working set of instructions, such as instructions loaded from the instruction memory 207, in the working memory 202. Also, the processor 201 can use the working memory 202 to store dynamic data generated by the processing of the computing device 200. The working memory 202 is a random access memory (RAM) such as a static random access memory (SRAM) or a dynamic random access memory (DRAM), or other suitable memory.

[0042] The input / output device 203 can include suitable devices that enable data input and output. For example, the input / output device 203 can include one or more of a keyboard, a touchpad, a mouse, a stylus, a touch screen, physical buttons, a speaker, a microphone, or other suitable input / output devices.

[0043] The communication port 209 includes, for example, a serial port such as a universal asynchronous receiver / transmitter (UART) connection, a universal serial bus (USB) connection, or other suitable communication port or connection. In one embodiment, the communication port 209 enables programming of executable instructions in the instruction memory 207. In one embodiment, the communication port 209 enables transfer (e.g., upload or download) of data such as image data.

[0044] The display 206 can be an appropriate display, such as a 3D viewer or a monitor. The display 206 can display the user interface 205. The user interface 205 enables interaction between the computing device 200 and the user. For example, the user interface 205 can be the user interface of an application that enables a user (e.g., a medical professional) to browse or operate on a model and define the target area for treating a patient as described herein. In one embodiment, the user can interact with the user interface 205 by using the input / output device 203. In one embodiment, the display 206 is a touch screen, and the user interface 205 is displayed on the touch screen. In one embodiment, the display 206 displays an image of scanned image data (e.g., an image slice).

[0045] The transceiver 204 enables communication with a network such as the communication network 118 of FIG. 1. For example, if the communication network 118 of FIG. 1 is a cellular network, the transceiver 204 is configured to enable communication with the cellular network. In one embodiment, the transceiver 204 can be selected based on the type of the communication network 118 in which the radiation ablation narrowing computing device 200 will operate. One or more processors 201 can be operative to receive data from a network such as the communication network 118 of FIG. 1 via the transceiver 204 and transmit data to the network.

[0046] Referring once again to FIG. 1, the database 116 can be a remote storage device (e.g., including non-volatile memory), such as a cloud-based server, a disk (e.g., a hard disk), a memory device of another application server, a networked computer, or other suitable remote storage. In one embodiment, the database 116 can be a local storage device, such as a hard drive, non-volatile memory, or a USB stick, for one or more of the target recommendation computing device 104 and the treatment planning computing device 106.

[0047] The communication network 118 can be a WiFi (registered trademark) network, a cellular network such as a 3GPP (registered trademark) network, a Bluetooth (registered trademark) network, a satellite network, a wireless local area network (LAN), a network utilizing a radio frequency (RF) communication protocol, a near field communication (NFC) network, a wireless metropolitan area network (MAN) connecting multiple wireless LANs, a wide area network (WAN), or other suitable network. The communication network 118 can provide access to, for example, the Internet.

[0048] The imaging device 102 is configured to scan an image such as an image of a patient's organ, and provide image data 103 (e.g., measurement data) that identifies and characterizes the scanned image to the communication network 118. Alternatively, the imaging device 102 is configured to acquire an electrical imaging such as a heart ECG image. For example, the imaging device 102 can scan a patient's structure (e.g., an organ), and send image data 103 that identifies one or more slices of the scanned structure's 3D volume to one or more of the target recommendation computing device 104 and the treatment planning computing device 106 via the communication network 118. In one embodiment, the imaging device 102 stores the image data 103 in the database 116, and one or more of the target recommendation computing device 104 and the treatment planning computing device 106 can retrieve the image data 103 from the database 116.

[0049] In one embodiment, the target recommendation computing device 104 is configured to communicate with the treatment planning computing device 106 through the communication network 118. In one embodiment, the target recommendation computing device 104 and the treatment planning computing device 106 communicate with each other via the database 116 (e.g., by storing data in the database 116 and retrieving data from the database 116). In one embodiment, one or more target recommendation computing devices 104 and one or more treatment planning computing devices 106 are part of a cloud-based network that enables sharing of resources and communication with each device.

[0050] In one embodiment, one or more target-recommended computing devices 104 are located in a first area 122 of the medical facility 120, and one or more target-recommended computing devices 104 are located in a second area 124 of the medical facility 120. Thereby, the cardiac radiation ablation narrowing system 100 enables multiple electrophysiologists (EPs) to cooperate to finalize the target area. For example, one EP can operate the first target-recommended computing device 104 in the first area 122, and another EP can operate the second target-recommended computing device 104 in the second area 124. The first target-recommended computing device 104 and the second target-recommended computing device 104 can communicate through the communication network 118 by transmitting and receiving data related to (e.g., defining) the target area (e.g., the proposed target area). Each of the EPs can operate the corresponding target-recommended computing device 104 to adjust the target area, and when both EPs agree on the target area, the target area can be finalized.

[0051] [Target Area Recommendation] As described herein, the target-recommended computing device 104 can execute an application that generates a user interface (e.g., user interface 205) that can be presented to a medical professional such as an EP. The executed application helps a medical professional define a target area for a patient to be treated. For example, an electrophysiologist (EP) can operate the target-recommended computing device 104 to define a target area for treating a patient. The target-recommended computing device 104 can recommend a target area (e.g., an initial target area) to be treated based on patient data such as image data 103 captured by the imaging device 102 regarding the patient.

[0052] In determining the initial target area, the target-recommended computing device 104 can analyze the image data and execute one or more processes to identify the initial target area. The initial target area can include, for example, the scar location. For example, the target-recommended computing device 104 can apply one or more machine learning processes (e.g., models, algorithms) to the image data to define the initial target area. The machine learning process is trained using supervised or unsupervised learning and / or based on features generated from past image scans. For example, the first machine learning process is trained with features generated from CT data characterizing previous CT scans, the second machine learning process is trained with features generated from MR data characterizing previous MR scans, and the third machine learning process is trained with features generated from PET data characterizing previous PET scans.

[0053] Furthermore, based on the scar location, the target-recommended computing device 104 can identify healthy parts of the organ. In one embodiment, the target-recommended computing device 104 determines the healthy parts based on applying one or more rules to the determined location (e.g., three-dimensional location) of the scar within the organ. For example, the target-recommended computing device 104 can identify an area of the organ that is at least minimally distant from the scar location as a healthy part of the organ.

[0054] In one embodiment, the target-recommended computing device 104 obtains the patient's electrocardiogram (EKG) data and determines the initial target area based on the EKG data. For example, the target-recommended computing device 104 can apply a trained machine learning process to the EKG data to determine the initial target area as described herein. In one embodiment, the trained machine learning process is applied to one or more of MR image data, CT image data, PET image data, and EKG image data to determine the initial target area.

[0055] In one embodiment, the target-recommending computing device 104 determines an initial target region based on report data characterizing findings and / or diagnoses of a patient by a medical expert. For example, the database 116 may store report data characterizing medical reports. The medical reports may include descriptions of medical conditions, areas of concern, location information (e.g., the location of an organ region with scarring), physical condition information, medical expert findings, patient diagnoses, or any other medical information. The target-recommending computing device 104 can obtain report data regarding the patient from the database 116 and apply a text extraction process to the report data to identify the text. Further, in one embodiment, the target-recommending computing device 104 can apply a trained machine learning process to the text data in addition to the image data to determine the initial target region.

[0056] In one embodiment, the report data characterizes audio, such as the voices of one or more medical experts, for example. The target-recommending computing device 104 can apply one or more audio-to-text (speech recognition) models to the report data to extract text data. For example, the target-recommending computing device 104 can apply a speech recognition algorithm to the report data to extract the text.

[0057] In one embodiment, the target recommendation computing device 104 applies one or more rules to text data and / or image data to determine an initial target region that may include a scar location. For example, the database 116 may store rule data characterizing one or more rules configured by one or more medical experts. The rules can, for example, associate one or more words of text with a first target region and one or more other words with a second target region. The target recommendation computing device 104 determines, for example, whether text extracted from the report data includes either one or more words associated with the first target region or one or more other words associated with the second target region. Based on any corresponding words, the target recommendation computing device 104 can determine either the first target region or the second target region as the initial target region. In one embodiment, the target recommendation computing device 104 determines the initial target region as the target region with the most corresponding words. In one embodiment, the target recommendation computing device 104 applies one or more rules to text extracted from the report data to determine healthy portions.

[0058] Furthermore, in one embodiment, the target-recommended computing device 104 can associate the first target region with a part of the organ model, for example, a specific segment of the organ's segment model. For example, FIG. 4 illustrates a 17-segment model 402 of the heart ventricles, which is displayed, for example, by the GUI 400. Each of the 17 segments is identified by a model key 404 and corresponds to a portion of the heart ventricle. For example, segment 1 corresponds to the basal anterior wall portion of the heart ventricle, and segment 17 corresponds to the apex portion of the heart ventricle. The target-recommended computing device 104 determines the segment of the 17-segment model 402 corresponding to the first target region. In one embodiment, the target-recommended computing device 104 determines the segment based on the relative position of the first target region with respect to a part of the heart, such as the apex. For example, the target-recommended computing device 104 can determine the distance and direction from the apex of the heart to the first target region of the heart and determine the corresponding segment based on this distance and direction. In one embodiment, the target-recommended computing device 104 determines the corresponding segment based on one or more rules. This rule can identify, for example, the correlation between one or more words of the text (extracted from the report data, for example) and a specific segment.

[0059] In one embodiment, the target recommended computing device 104 determines segments of a model based on the image data received by each of a plurality of imaging techniques. For example, the target recommended computing device 104 retrieves CT image data, MR image data, and PET image data regarding a patient from the database 116. The target recommended computing device 104 may determine segments of the segmentation model based on each of the patient's CT image data, MR image data, and PET image data. Further, the target recommended computing device 104 can determine whether these determined segments are the same (e.g., match). If they are the same, the target recommended computing device 104 generates segment data characterizing the determined segments and stores this segment data in the database 116. If the determined segments are not the same, the target recommended computing device 104 may apply one or more additional rules to the determined segments to generate segment data. For example, the target recommended computing device 104 determines the number of times a particular segment was determined and generates segment data identifying the most frequently determined segment.

[0060] In one embodiment, the target recommendation computing device 104 may apply weights to each of the determined segments and generate target data based on the weighted segments. For example, the target recommendation computing device 104 may apply a 40% weight to the PET image data and a 30% weight to each of the segments determined based on the MR image data and the CT image data. If the three determined weights are different, the target recommendation computing device 104 may select the segment determined based on the PET image data. If the segments determined based on the MR image data and the CT image data are the same, the target recommendation computing device 104 may select the determined segment over the segment determined by the PET image data (e.g., 60% exceeds 40%).

[0061] The target recommendation computing device 104 may provide the first target region and / or the determined segments of the model for display. For example, the target recommendation computing device 104 may reconstruct an image based on the received image data, and the reconstructed image identifies the first target region. The reconstructed image may be, for example, a two-dimensional or three-dimensional image. For example, the first target region may be a different color from the other parts of the organ. In one embodiment, the target recommendation computing device 104 may outline, highlight, or mask the first target region in the reconstructed image, or identify the first target region in the reconstructed image in other suitable ways. Further, the target recommendation computing device 104 may provide the reconstructed image for display. Thereby, medical experts such as EPs can easily identify the first target region.

[0062] In one embodiment, the target recommended computing device 104 displays, additionally or alternatively, the segment model described herein. In one embodiment, the target recommended computing device 104 can outline, highlight, or shade the determined segment, or can identify the determined segment in other suitable ways. In one embodiment, the target recommended computing device 104 provides a reconstructed image for display overlaid on the segment model. For example, the EP can view the scar region identified in the reconstructed image overlaid on a 17-segment heart ventricle model. In one embodiment, the target recommended computing device 104 provides the segment model for display overlaid on the reconstructed image.

[0063] Further, in one embodiment, the target recommended computing device 104 displays a segment model that identifies the scar location and healthy portions of an organ. For example, the target recommended computing device 104 can display a segment model having segments corresponding to scar locations that are displayed differently from segments corresponding to healthy portions of the organ. For example, the segments corresponding to the scar locations can be displayed, highlighted, or shaded in a different color from the segments corresponding to healthy portions of the organ.

[0064] [Target Region Adjustment Guidance] The target recommended computing device 104 enables medical experts such as EPs to modify, change, or update target areas such as the recommended target areas described herein. After the final decision, the target recommended computing device 104 can generate target definition data that identifies the target area finally determined for the patient, and can transmit this target definition data to the treatment planning computing device 106. Medical experts such as radiation oncologists can operate the treatment planning computing device 106 to treat the patient in the area of the patient defined by the target definition data using the imaging device 102. In one embodiment, the target definition area is incorporated into a radiation ablation treatment plan for treating the patient.

[0065] The application executed by the target recommended computing device 104 facilitates modifications, changes, or updates to the recommended target area (e.g., the initial target area). For example, FIG. 5A shows a graphical user interface (GUI) 520 of a display interface 500 that includes an interactive model 522. In this embodiment, the interactive model 522 is a 17-segment model representing segments of the heart ventricle. A medical expert can select or deselect one or more segments of the interactive model 522 that may correspond to the treatment target area. The interactive model 522, when first displayed to the medical expert, identifies the recommended segments corresponding to the area recommended as the treatment target (i.e., the recommended target area). In one embodiment, however, the interactive model 522 does not identify the recommended segments. In this embodiment, the recommended segments include a first segment 523A (e.g., segment 11). However, assume that the medical expert wants to mark additional segments as treatment targets. The medical expert only needs to select the additional segment in the interactive model 522 with the cursor 589 (e.g., using the input / output device 203).

[0066] For example, as shown in FIG. 5B, a medical professional can select a second segment 523B (e.g., segment 16) and a third segment 523C (e.g., segment 15). Similarly, the medical professional can also deselect any of the selected segments. In one embodiment, when a cursor 589 is placed over a segment (e.g., segment 4), the GUI 520 displays the name of that segment (e.g., using a pop-up window). In this embodiment, there is a cursor 589 over segment 4 of the interactive model 522, and in response, the GUI 520 displays a name box 525 that identifies segment 4 as the "basal inferior" part of the heart ventricle base wall.

[0067] To add a segment to the recommended target area, the medical professional clicks on an add (ADD) icon 590. In response, the target recommendation computing device 104 generates data that identifies and characterizes the updated target area and stores the generated data in a data repository such as within the database 116. If the medical professional wishes to redo segment selections and deselections without saving, the medical professional can click on a cancel (CANCEL) icon 592. As a result, all selections or deselected segments since the add icon 590 was last clicked are discarded. In one embodiment, the GUI 520 includes a reset (RESET) icon 593, and when this is selected, any modifications made by the medical professional are cleared and the system returns to the first recommended segments (e.g., the ones initially recommended).

[0068] Assuming that, for example, some changes have been made, when the healthcare professional completes the changes to the recommended segment, the healthcare professional can select the COMPLETE icon 594. In accordance with the selection of the COMPLETE icon 594, the running application displays the GUI 550 shown in FIG. 5C. The GUI 550 includes an interactive model 560 that identifies the selected segment 562 (e.g., the one selected in the GUI 520). The selected segment 562 can be identified in an appropriate manner and, in this embodiment, as indicated by the key 561. For example, the selected segment can be displayed in a different color from the non-selected segments. In one embodiment, the selected segment can be highlighted and / or shaded (e.g., so as to be different from the non-selected segments) and / or identified by a segment number. Further, the healthcare professional can adjust the selected segment by, for example, selecting and / or deselecting segments within the interactive model 560 as described with respect to the interactive model 522.

[0069] Furthermore, the GUI 550 may include one or more survey category maps (e.g., a "Heat Map") that characterize previous surveys and treatments of the same patient. For example, the GUI 550 includes an Electrical map 574, a Structural map 578, and a Composite map 570. The Electrical map 574 characterizes previous electrical surveys and treatments, such as those based on EKG results. A key 576 corresponding to the Electrical map 574 provides an indication of the relative number of times each segment has been previously selected in electrical surveys and / or treatments related to the patient. For example, the key 576 can indicate the Most selected segment and the Never / Least selected segment. In one embodiment, each of the categories indicated by the key 576 corresponds to a range of the number of times each segment has been selected (e.g., the first category is 0 times, the second category is 1 time, the third category is 2 - 4 times, the fourth category is 5 - 7 times, and the fifth category is 8 or more times). The key 576 can provide the indication using a suitable method, such as a hatching method or a change in the display color of the segment. In this embodiment, for example, segment 3 has been previously selected more often than segments 4 and 6. Similarly, the Structural map 578 can characterize previous imaging surveys and treatments, such as those based on CT, MR, or PET images. A key 580 corresponding to the Structural map 578 provides an indication of the relative number of times each segment has been previously selected in imaging surveys and / or treatments related to the patient. In this embodiment, segment 5 has been previously selected more often than any other segment.

[0070] The composite map 570 is based on the relative number of times segments have been previously selected in electrical and structural surveys characterized by an electrical map 574 and a structural map 578. For example, the target recommended computing device 104 can determine the total number of times each segment has been selected in both the electrical survey and the structural survey, and can determine how frequently each segment has been selected compared to other segments. A key 572 corresponding to the composite map 570 provides an indication of the relative number of times each segment has been previously selected in all surveys and / or treatments related to the patient. For example, the key 572 can indicate the most selected segment and the never / least selected segment. In one embodiment, each of the categories indicated by the key 572 corresponds to a range of the number of times each segment has been selected. The key 572 can provide the indication using an appropriate method, such as a shading method or a change in the display color of the segment.

[0071] In one embodiment, the target recommended computing device 104 can apply a weighting to the number of times each segment has been selected with respect to the type of previous survey. For example, the target recommended computing device 104 can weight the structural survey more heavily than the electrical survey, or vice versa. In accordance with the application of the weighting, the target recommended computing device 104 determines how frequently each segment has been selected compared to others. In this embodiment, a first weighting 575 is applied to the electrical survey and a second weighting 579 is applied to the structural survey. In FIG. 5C, the first weighting 575 and the second weighting 579 are the same (e.g., w: 0.5). However, they may be different. In fact, in one embodiment, the GUI 550 enables a medical expert to edit each of the first weighting 575 and the second weighting 579.

[0072] By providing an investigation category map (e.g., an electrical map 574, a structural map 578, and a composite map 570), the GUI 550 provides additional information to the medical professional so that the segment most suitable for treatment is reliably selected.

[0073] Furthermore, the GUI 550 may include a portion of sample images 563 that display the patient's image scan and / or the image scans of other patients (with similar health conditions and / or treatments). For example, the target recommended computing device 104 can determine one or more previous patients with similar health conditions and / or treatments and obtain the image data 103 of the current patient and the one or more previous patients from the database 116. Furthermore, the target recommended computing device 104 can reconstruct an image based on the obtained image data and display the image in a portion of the sample images 563 of the GUI 550.

[0074] The GUI 550 can further display segment-based notes 564, which may include text that has already been determined and provided for each selected segment. For example, since segments 11, 15, 16 are selected in the interactive model 560, the notes for each of these segments are displayed in a portion of the segment-based notes 564 of the GUI 550. This note includes, for example, text pre-approved by one or more medical professionals. In one embodiment, additional information can be input by the medical professional into the segment-based notes 564 (e.g., via the input / output device 203).

[0075] The GUI 550 further includes a portion of ALERTS 565 that can provide warnings (e.g., cautions, recommended checks, advice, etc.) based on the selected segments. For example, the target recommended computing device 104, as described herein, can generate warnings based on the application of one or more rules or, in one embodiment, based on the application of one or more machine learning processes to the patient's image data and / or report data. For example, based on the patient's previous examinations, if the target recommended computing device 104 determines that the scar location is located in a particular segment beyond a threshold amount or percentage of times (e.g., 75%) and that segment is not currently selected (e.g., in the interactive model 560), the target recommended computing device 104 can display a warning. As another example, if the target recommended computing device 104 determines that segments exceeding a threshold amount (e.g., 3) are selected, the target recommended computing device 104 can display a warning. In yet another example, if the target recommended computing device 104 determines that a particular combination of segments is selected or not selected (e.g., when segments 3 and 7 are selected, when segment 15 is selected but segment 10 is not selected, etc.), the target recommended computing device 104 can display a warning. Such rules can be user-defined rules and can be based on the agreement of one or more medical experts (e.g., a consortium of medical experts who agree on best practices).

[0076] To illustrate other rules, it may include determining that a scar segment is selected at or near the ventricular (VT / ventricular tachycardia) EXIT SITE with the goal of avoiding a healthy tissue. Another rule may include limiting the number of target segments based on the number of induced VTs. For example, the rule may permit 1 to 2 target segments for a VT induced once, 1 to 4 target segments for a VT induced twice, and 1 to 6 target segments for a VT induced three or more times. In one embodiment, the rule may specify a maximum number of target segments to be selected (such as 6).

[0077] Furthermore, the GUI 550 includes a portion of a feedback request 566 that enables a medical expert to request input (e.g., opinions) from other medical experts. For example, a medical expert can provide input in the portion of the feedback request 566 of the GUI 550, and the target recommendation computing device 104 can send the request to one or more other computing devices such as another target recommendation computing device 104. In one embodiment, the request is sent to one or more predetermined computing devices. In one embodiment, the portion of the feedback request includes a menu (e.g., a drop-down menu) that enables selection of one or more medical experts to whom the request is to be sent. The receiving computing device displays the request, enables a medical expert to provide an answer, and may further reply with the answer to the target recommendation computing device 104 that sent the request. The target recommendation computing device 104 that received the answer may display the answer in the portion of the feedback request 566.

[0078] FIG. 6A illustrates an alignment GUI 601 of a display interface 500 that may be generated, for example, by a target recommended computing device 104. The display interface 500 includes a 3D structure image 602 that includes a 3D segment model 606 superimposed on a scanned image 604. The target recommended computing device 104 can generate the 3D structure image 602 based on image data regarding a patient (e.g., image data 103) and an interactive model (e.g., interactive model 522 or interactive model 560).

[0079] The 3D segment model 606 is, for example, a 3D segment model of a heart ventricle. The scanned image 604 can be an image scanned by an image scanning device 102, such as a 3D volume of a scanned structure of a patient. And the 3D structure image 602 includes a target area map 648 that defines a target area to be treated for the patient. The target area map 648 corresponds to at least initially (e.g., before adjustment by the EP), one or more selected target areas of the interactive model, such as the first, second, and third segments 523A, 523B, 523C of the interactive model 522, or the selected segment 562 of the interactive model 560. In one embodiment, the target area map 648 is displayed in a special color. In one embodiment, the target area map 648 is displayed using special hatching, or other suitable mechanisms are used to enable the EP to easily determine the contour of the target area map 648. Further, a vertical axis 650 is displayed and extends through the apex 608 of the 3D structure image 602.

[0080] In one embodiment, the GUI 601 can display a reference character 680. The reference character 680 is displayed from a viewpoint corresponding to the orientation of the 3D structure image 602. For example, when the orientation of the 3D structure image 602 is displayed from an overhead viewpoint as if the corresponding organ is in the patient's body, the reference character 680 is displayed from the overhead viewpoint. Thereby, medical experts such as EPs can easily determine the current viewpoint and / or orientation at which the 3D structure image 602 is being displayed.

[0081] In one embodiment, the GUI 601 includes one or more adjustment icons 655 that enable adjustment of the 3D structure image 602. For example, the adjustment icon 655 enables functions such as zoom in, zoom out, pan, and rotation.

[0082] Referring to FIG. 6B, the GUI 601 can display one or more drag points, such as drag points 670A and 670B, that enable the EP to perform adjustments on the 3D structure image 602. For example, the EP can adjust the vertical axis 650 by dragging the drag point 670A to a new position. Accordingly, the GUI 601 adjusts the orientation of the scanned image 604 with respect to the 3D segment model 606. Similarly, the EP can adjust the target area map 648 by dragging the drag point 670B to a new position. In one embodiment, the GUI 601 enables the creation or deletion of drag points. For example, the EP can right-click on a drag point such as the drag point 670B and select a "Delete" option to delete the drag point. Similarly, the EP can right-click on a part of the 3D segment model 606 and select an "Add" option to add a drag point.

[0083] FIG. 6C shows the 3D structure image 602 after the EP provides an input to rotate the 3D structure image 602 clockwise about the vertical axis 650 (e.g., using the input / output device 203 to select one or more adjustment icons 655). In this embodiment, the EP can adjust the anterior interventricular groove 686 of the 3D structure image 602 by the drag point 670C.

[0084] Also, the adjustment icon 655 can enable the EP to display images of additional organs, such as organs adjacent to the organ identified by the scanned image 604. For example, referring to FIG. 6D, the EP can select the adjustment icon 655 to display the organ selection box 675, and by this organ selection box 675, the EP can select what to display from one or more organs.

[0085] For example, assuming that the EP selects "Lung" (e.g., "Lung_r_p" for the right lung and "Lung_l_p" for the left lung) and "Esophagus", the GUI 601 will display the rendering (e.g., 3D rendering) of the first organ 685 (e.g., the lung) and the second organ 687 (e.g., the esophagus) as shown in FIG. 6E. The rendering is, for example, a 3D model pre-stored in the database 116. In other embodiments, the rendering is a scanned image of the corresponding structure of the patient.

[0086] Furthermore, in one embodiment, the GUI 601 can further display the distances 677 from the organ to be treated (e.g., the heart ventricle) to each of the other organs. In one embodiment, the target-recommended computing device 104 can determine the distances from the center of the scar position of the organ to be treated to each of the other organs based on, for example, the image data regarding the patient (e.g., the image data 103). In one embodiment, the target-recommended computing device 104 determines the distances based on the text extracted from the report data as described herein. For example, the target-recommended computing device 104 can identify the text describing the position of another organ together with the text describing the scar position, and can determine the distance between the scar position and the other organ based on that position.

[0087] FIG. 3 illustrates a part of the target-recommended computing device 104. In this embodiment, the target-recommended computing device 104 includes an image reconstruction engine 302, a target recommendation engine 304, a user target selection guidance engine 306, and an alignment determination engine 308. In one embodiment, one or more of the image reconstruction engine 302, the target recommendation engine 304, the user target selection guidance engine 306, and the alignment determination engine 308 are implemented in hardware. In one embodiment, one or more of the image reconstruction engine 302, the target recommendation engine 304, the user target selection guidance engine 306, and the alignment determination engine 308 are implemented as executable programs stored in a tangible non-transitory memory such as the instruction memory 207 of FIG. 2 and executed by one or more processors such as the processor 201 of FIG. 2.

[0088] In this embodiment, one or more of the target recommendation engine 304, the user target selection guidance engine 306, and the alignment determination engine 308 may receive one or more user inputs 301. For example, a medical expert can provide one or more user inputs 301 via the input / output device 203 or via the touch screen of the display 206. The user input 301 may be received in a graphical user interface (GUI) provided by the running application. Each of the target recommendation engine 304, the user target selection guidance engine 306, and the alignment determination engine 308 can receive data (e.g., user input 301) from the GUI and provide data such as display data to the GUI.

[0089] The image reconstruction engine 302 obtains image data 103 regarding a patient from the database 116. For example, the image data 103 may be image data such as CT image data or MR image data regarding a patient captured by the image scanning device 102. The image reconstruction engine 302 reconstructs an image based on the obtained image data 103. In one embodiment, the reconstructed image may be a three-dimensional image of one or more organs of the patient. The image reconstruction engine 302 generates image reconstruction data 303 characterizing the reconstructed image and provides this image reconstruction data 303 to the target recommendation engine 304.

[0090] The target recommendation engine 304 can execute a process for identifying a first target region to be treated based on the image reconstruction data 303. For example, the target recommendation engine 304 can apply one or more trained machine learning processes to the image reconstruction data 303 to define the first target region. The machine learning process can be trained using supervised or unsupervised learning based on features generated from past image scans, as described herein.

[0091] In one embodiment, the target recommendation engine 304 determines an initial target area based on patient data 310 regarding a patient obtained from the database 116. The patient data 310 characterizes medical information regarding the patient, such as medical reports, previous treatments, current and past health conditions, diagnoses, current and past treatments, and further other medical information. For example, the patient data 310 can include report data characterizing the findings and / or diagnoses of the patient by medical experts. The target recommendation engine 304 can obtain the patient data 310 regarding the patient from the database 116 and apply a text extraction process to the patient data 310 to identify text. Further, the target recommendation engine 304 can apply a trained machine learning process to the text data in addition to the image reconstruction data 303 in one embodiment to determine the initial target area.

[0092] In one embodiment, the target recommendation engine 304 applies one or more rules to the text data and / or the image reconstruction data 303 to determine the initial target area. The rules can, for example, associate one or more words of the text data with a first target area and associate another one or more words of the text data with a second target area. The target recommendation engine 304 can determine, for example, whether the extracted text includes any of one or more words related to the first target area or whether it includes any of another one or more words related to the second target area. Based on the corresponding words, the target recommendation engine 304 can determine the first target area as the first target area or the second target area. In one embodiment, the target recommendation engine 304 determines the area with the most corresponding words as the initial target area.

[0093] The target recommendation engine 304 generates recommendation target data 305 that characterizes the determined first target region. The recommendation target data 305 can identify the first target region in the reconstructed image and, additionally or alternatively, identify the corresponding segment of the segment model as described herein. The target recommendation engine 304 provides the recommendation target data 305 to the user target selection guidance engine 306.

[0094] The user target selection guidance engine 306 enables a medical expert to update the first target region. For example, the user target selection guidance engine 306 can generate one or more GUIs, such as GUIs 520, 550, that enable a medical expert to change, update, or modify the model segment corresponding to the treatment region. In one embodiment, the user target selection guidance engine 306 can display an interactive model, such as interactive model 522 or interactive model 560, and receive an input (e.g., input 301) for selecting or deselecting segments of the interactive model. The user target selection guidance engine 306 updates the interactive model accordingly based on the input. Additionally, one or more GUIs can also display a sample image, such as in the portion of sample image 563 of GUI 550 as described herein. In addition, one or more GUIs can display segment-based notes, such as in the portion of segment-based note 564 of GUI 550 as described herein, and can further provide a warning, such as in the portion of warning 565 of GUI 550. The user target selection guidance engine 306 can update the displayed segment-based notes and / or warning as the medical expert selects and / or deselects segments of the interactive model. Further, the user target selection guidance engine 306 can generate user selection target data 307 that characterizes the selected segments and can provide the user selection target data 307 to the alignment determination engine 308.

[0095] The alignment determination engine 308 executes a process of generating and providing a 3D model of an organ corresponding to the user-selected target data 307 or a portion of the organ for display. Further, the alignment determination engine 308 can receive image reconstruction data 303 characterizing the reconstructed image from the image reconstruction engine 302, which, in one embodiment, is a 3D image of the patient's heart ventricle. The alignment determination engine 308 can determine the alignment of the reconstructed image with respect to the 3D model, and overlay the 3D model on the reconstructed image according to the determined alignment to generate a 3D structure image. Then, the alignment determination engine 308 can provide the 3D structure image for display, for example, to the display 206.

[0096] Further, the alignment determination engine 308 can receive one or more user inputs 301 that specify and characterize adjustments to the 3D structure image. In response to the user input 301, the alignment determination engine 308 can adjust the 3D structure image accordingly. For example, the alignment determination engine 308 can make the alignment of the 3D model with respect to the reconstructed image more accurate.

[0097] In one embodiment, the alignment determination engine 308 determines whether each adjustment by a medical expert violates one or more predetermined rules (e.g., from the user-selected rule data 312 of the database 116). If the adjustment violates a rule, the alignment determination engine 308 can display a pop-up message with a warning.

[0098] In one embodiment, the alignment determination engine 308 receives one or more user inputs 301 that identify a selection of one or more other organs to be displayed in conjunction with the 3D structural image. In response, the alignment determination engine 308 provides a 3D model of the organ for display. In one embodiment, the alignment determination engine 308 provides the image data 103 of the corresponding organ of the patient for display. In one embodiment, the alignment determination engine 308 determines the distance between the organ to be treated and each of the one or more other selected organs, and provides the determined distance for display.

[0099] In one embodiment, the alignment determination engine 308 receives one or more user inputs 301 that identify a pan or zoom operation. In response, the alignment determination engine 308 can pan or zoom across the 3D structural image. In one embodiment, the alignment determination engine 308 receives one or more user inputs 301 that identify a selection of a preconfigured option for a particular viewpoint of the 3D structural image. The alignment determination engine 308 can adjust the 3D structural image according to the selected particular viewpoint and display the adjusted 3D structural image.

[0100] The alignment determination engine 308 generates target definition data 309 that identifies and characterizes one or more of the aligned 3D structural images, the other selected organs, and the determined distances, and can store this target definition data 309 in the database 116. In one embodiment, the alignment determination engine 308 causes the target recommendation computing device 104 to transmit the target definition data 309 to another computing device, such as the treatment planning computing device 106, for treating the patient.

[0101] FIG. 7 illustrates a flowchart of a method 700 executable by, for example, a target recommended computing device 104. Beginning at step 702, the target recommended computing device 104 receives image data regarding a patient. For example, the target recommended computing device 104 can obtain the image data 103 from the database 116 or receive the image data 103 from the image scanning device 102. At step 704, the target recommended computing device 104 receives report data regarding the patient. For example, the target recommended computing device 104 can obtain patient data 310 regarding the patient from the database 116. At step 706, the target recommended computing device 104 applies a text extraction process to the report data to identify text data. The target recommended computing device 104 can apply any known text extraction process suitable for extracting text from a report, for example.

[0102] At step 708, the target recommended computing device 104 determines a target area to recommend for treatment based on the image data and the text data. For example, as described herein, the target recommended computing device 104 can apply one or more trained machine learning processes or apply one or more rules to the image data and the text data to determine the target area to recommend. At step 710, the target recommended computing device 104 receives a first input identifying a change to the recommended target area. For example, a medical expert can select or deselect segments of a corresponding interactive model (e.g., the interactive model 522 or the interactive model 560).

[0103] In step 712, the target recommended computing device 104 applies one or more rules to the changes to the target area to be recommended, and in step 714, determines whether there is one or more rule violations. If there are no rule violations, the method proceeds to step 716, and the target recommended computing device 104 applies the change to the target area to be recommended (for example, the corresponding model is saved in the database 116 with the selected segment or the deselected segment). Then, the method proceeds to step 724, and the target area to be recommended is updated and displayed. For example, the target area to be recommended can be displayed in the GUI.

[0104] On the other hand, in step 714, if the target recommended computing device 104 determines that there is at least one rule violation, the method proceeds to step 718, and the target recommended computing device 104 displays an error message requesting approval of the change. For example, the target recommended computing device 104 displays a caution message asking the medical expert to verify the change, and further, for example, can display one or more warnings in the warning part of the GUI and / or one or more segment-based notes in the segment-based note part of the GUI.

[0105] The method proceeds from step 718 to step 720, and the target recommended computing device 104 receives a second input. The second input specifies approval or cancellation of the change. For example, the error displayed in step 718 may include an approval icon and a cancellation icon. The medical expert can select the approval icon to approve the change or the cancellation icon to cancel the change.

[0106] In step 722, the target recommended computing device 104 determines whether the change is approved based on the second input. If the change is approved, the method proceeds to step 716 and the change is applied. On the other hand, if the change is not approved, the method proceeds to step 724 and the recommended target area is displayed without change. Then, the method ends.

[0107] Figure 8 is a flowchart illustrating a method 800 that can be executed, for example, by a target recommended computing device 104. The method begins at step 802 where patient image data is received. For example, the target recommended computing device 104 can obtain the image data 103 from the database 116 or receive the image data 103 from the image scanning device 102. In step 804, the target recommended computing device 104 determines the scar position based on the image data. For example, as described herein, the target recommended computing device 104 can determine the scar position based on applying one or more trained machine learning processes and / or one or more rules to the image data.

[0108] In step 806, the target recommended computing device 104 determines the segment of the model based on the scar position. For example, the target recommended computing device 104 can determine the segment of a segment model (e.g., a 17-segment model of the heart ventricle) corresponding to the scar position. In step 808, the target recommended computing device 104 displays the segment model along with the metrics of the determined segment. For example, as described herein, the target recommended computing device 104 can display the determined segment in a different color, highlight or shade the determined segment, or otherwise identify the determined segment in an appropriate manner. Then, the method ends.

[0109] Figure 9 is a flowchart illustrating a method 900 that can be executed by, for example, a target-recommended computing device 104. Starting from step 902, image data of a patient is received. For example, the target-recommended computing device 104 can obtain the image data 103 from the database 116 or receive the image data 103 from the image scanning device 102. At step 904, the target-recommended computing device 104 determines the scar position of the organ based on the image data. For example, as described herein, the target-recommended computing device 104 can determine the scar position of the organ based on applying one or more trained machine learning processes and / or one or more rules to the image data.

[0110] At step 906, the target-recommended computing device 104 determines the healthy part of the organ based on the scar position. For example, as described herein, the target-recommended computing device 104 can identify, as the healthy part of the organ, the part of the organ that is at least minimally distant from the scar position. In one embodiment, the target-recommended computing device 104 applies one or more rules to the text extracted from the report data to determine the healthy part.

[0111] At step 908, the target-recommended computing device 104 displays the segmentation model along with the identification of the scar position and the healthy part of the organ. For example, as described herein, the target-recommended computing device 104 can display the segmentation model with the segment corresponding to the scar position as a different display from the segment corresponding to the healthy part of the organ. For example, the segment corresponding to the scar position can be displayed in a different color, highlighted, shaded, etc. compared to the segment corresponding to the healthy part of the organ. Then, the method ends.

[0112] In one embodiment, a computing device receives image data from one or more modalities regarding a patient. The computing device determines a target region recommended as a treatment target based on the image data, and determines one or more corresponding segments of a segmentation model based on the recommended target region. Further, the computing device displays a segmentation model that identifies the determined one or more segments, and receives input data for modifying the determined one or more segments. Based on the input data, the computing device updates the one or more segments and generates target definition data that characterizes the updated one or more segments. The computing device transmits the target definition data to treat the patient.

[0113] In one embodiment, a system includes a database and a computing device connected to and communicating with the database. The computing device is configured to receive image data regarding a patient's organ. The computing device is also configured to determine a target region recommended as a treatment target for the organ based on the image data. Further, the computing device is configured to generate recommended target data that characterizes the recommended target region for the organ. The computing device is also configured to store the recommended target data in the database.

[0114] In one embodiment, a computing device receives report data characterizing a patient's medical findings and is configured to determine a recommended target region based on the report data. In one embodiment, the computing device is configured to determine a recommended target region by applying a text extraction process to the report data to identify text within the report data. In one embodiment, the computing device is configured to determine a recommended target region based on applying rules to the text.

[0115] In one embodiment, a computing device is configured to determine a target area to recommend based on applying one or more machine learning models to image data. In one embodiment, a computing device is configured to generate features based on past image scans and train one or more machine learning models based on the generated features.

[0116] In one embodiment, a computing device is configured to send target data to be recommended to a second computing device for treating a patient.

[0117] In one embodiment, a computing device is configured to receive a first input identifying a change to a target area recommended as a treatment target. Also, the computing device is configured to determine whether there is a violation of a first rule based on the change to the target area recommended as a treatment target. Further, the computing device is configured to provide an indication of whether the change is acceptable for display based on determining the presence or absence of one or more rule violations.

[0118] In one embodiment, a computing device is configured to update the recommended target area based on the change when it determines that there is no violation of the first rule.

[0119] In one embodiment, a computing device is configured to display an error message in accordance with the violation when it determines that there is a violation of the first rule.

[0120] In one embodiment, a computing device is configured to receive a second input, generate target data characterizing the recommended target area, and send this target data to a second computing device for treating a patient.

[0121] In one embodiment, a computing device is configured to display an interactive model on a graphical user interface. The interactive model includes a plurality of segments, and a first input identifies a selection of at least one segment of the plurality of segments. In one embodiment, the computing device is configured to display a note associated with at least one segment of the plurality of segments. In one embodiment, a first rule is based on a particular combination of the plurality of segments. In one embodiment, the first rule is based on a maximum number of selections of the plurality of segments.

[0122] In one embodiment, a computing device is configured to acquire image data regarding a patient's organ. A target area recommended for treatment is in the organ. The computing device is also configured to generate a segment model based on the organ, and to display the segment model by overlaying the image data.

[0123] In one embodiment, a computing device is configured to acquire image data regarding a patient's organ. A target area recommended for treatment is in the organ. The computing device is also configured to generate a segment model based on the organ, and to display the image data by overlaying the segment model.

[0124] In one embodiment, a computing device is configured to generate a first digital model of an organ type and to determine an alignment of image data with respect to the first digital model. The computing device is further configured to generate a second digital model that includes at least a portion of the scanned image and the first digital model. The computing device is further configured to store the second digital model in a data repository. In one embodiment, the computing device is further configured to provide the second digital model for display. In one embodiment, the computing device is further configured to receive a second input that specifies an adjustment of the alignment of the image data with respect to the first digital model. The computing device is further configured to adjust the second digital model based on the second input. The computing device is further configured to store the adjusted second digital model in the data repository.

[0125] In one embodiment, the computing device is configured to receive a second input that identifies a treatment target region of an organ and, based on the treatment target region of the organ, to determine a corresponding portion of the second digital model. The computing device is further configured to regenerate the second digital model to identify the corresponding portion of the second digital model.

[0126] In one embodiment, a computing device is configured to receive image data regarding a patient. Also, the computing device is configured to determine a scar position of an organ based on the image data. Further, the computing device is also configured to determine any one of a plurality of segments of a model of the organ based on the scar position. Also, the computing device is configured to display a model that identifies the determined segment. For example, the computing device displays the determined segment in one color and the other segments of the plurality of segments in another color. In one embodiment, the computing device is configured to display the model by overlaying the image data. In one embodiment, the computing device is configured to display the image data by overlaying the model.

[0127] In one embodiment, a computing device is configured to receive image data regarding a patient. Also, the computing device is configured to determine a scar position of an organ based on the image data. Further, the computing device is configured to determine a healthy portion of the organ based on the scar position. Also, the computing device is configured to display a model of the organ that identifies the scar position and the healthy portion. For example, the computing device can display the scar position of the organ in one color and the healthy portion of the organ in another color.

[0128] In one embodiment, a method executed by a computer includes receiving image data regarding a patient. Also, the method includes determining a target area recommended as a treatment target based on the received image data. In one embodiment, the method also includes receiving report data regarding the patient. And the method includes determining a target area recommended as a treatment target based on the image data and the report data.

[0129] Furthermore, the method includes receiving an input that identifies a change to a target region recommended for treatment. The method also includes determining the presence or absence of one or more rule violations based on the change to the target region recommended for treatment. Additionally, the method includes providing an indication of whether the change is acceptable for display based on determining the presence or absence of one or more rule violations.

[0130] In one embodiment, the method includes receiving image data regarding a patient's organ. The method also includes determining a target region recommended for treatment of the organ based on the image data. Additionally, the method includes generating recommended target data characterizing the recommended target region of the organ. The method also includes including the recommended target data in a database.

[0131] In one embodiment, the method executed by a computer includes receiving a first input that identifies a change to a target region recommended for treatment. The method also includes determining whether the change violates a first rule based on the change to the target region recommended for treatment. Additionally, the method includes providing an indication of whether the change is acceptable for display based on determining the presence or absence of one or more rule violations.

[0132] In one embodiment, the method executed by a computer includes receiving image data regarding a patient. The method also includes determining a scar position of an organ based on the image data. Additionally, the method includes determining one of a plurality of segments of a model of the organ based on the scar position. The method also includes displaying the model with the identified segment. In one embodiment, the method includes displaying the model with the image data overlaid. In one embodiment, the method includes displaying the image data with the model overlaid.

[0133] In one embodiment, a method implemented by a computer includes receiving image data regarding a patient. The method includes determining a scar position of an organ based on the image data. Further, the method includes determining a healthy portion of the organ based on the scar position. Also, the method includes displaying a model of the organ with the scar position and the healthy portion identified.

[0134] In one embodiment, a non-transitory computer-readable medium storing instructions that, when executed by at least one processor, cause the at least one processor to perform a process including receiving image data regarding a patient. The process also includes determining a target region recommended as a treatment target based on the received image data. In one embodiment, the process also includes receiving report data regarding the patient. And the process includes determining a target region recommended as a treatment target based on the image data and the report data.

[0135] Further, the process includes receiving an input specifying a change to the target region recommended as a treatment target. The process also includes determining whether there is one or more rule violations based on the change to the target region recommended as a treatment target. Further, the process includes providing an indication of whether the change is acceptable for display based on the determination of whether there is one or more rule violations.

[0136] In one embodiment, a non-transitory computer-readable medium storing instructions that, when executed by at least one processor, cause the at least one processor to perform a process including receiving image data regarding a patient's organ. The process also includes determining a target region recommended as a treatment target for the organ based on the image data. Further, the process includes generating recommended target data characterizing the recommended target region of the organ. Also, the process includes including the recommended target data in a database.

[0137] In one embodiment, a non-transitory computer-readable medium storing instructions that, when executed by at least one processor, cause the at least one processor to perform a process including receiving a first input that identifies a change to a target region recommended for treatment. The process also includes determining whether the change violates a first rule based on the change to the target region recommended for treatment. Further, the process includes providing an indication of whether the change is acceptable for display based on a determination of the presence or absence of one or more rule violations.

[0138] In one embodiment, a non-transitory computer-readable medium storing instructions that, when executed by at least one processor, cause the at least one processor to perform a process including receiving image data regarding a patient. The process also includes determining a scar position of an organ based on the image data. Further, the process includes determining one of a plurality of segments of a model of the organ based on the scar position. The process also includes displaying the model with the identified segment. In one embodiment, the process includes displaying the model with the image data overlaid. In one embodiment, the process includes displaying the image data with the model overlaid.

[0139] In one embodiment, a non-transitory computer-readable medium storing instructions that, when executed by at least one processor, cause the at least one processor to perform a process including receiving image data regarding a patient. The process includes determining a scar site of an organ based on the image data. Further, the process includes determining a healthy portion of the organ based on the scar position. The process also includes displaying a model of the organ with the scar position and the healthy portion identified.

[0140] In one embodiment, a method executed by a computer includes means for receiving image data regarding a patient. Further, the method includes means for determining a target region recommended as a treatment target based on the received image data. In one embodiment, the method also includes means for receiving report data regarding the patient. And the method includes means for determining a target region recommended as a treatment target based on the image data and the report data.

[0141] Furthermore, the method includes means for receiving an input for specifying a change to the target region recommended as a treatment target. The method also includes means for determining the presence or absence of one or more rule violations based on the change to the target region recommended as a treatment target. Further, the method includes means for providing an indication of whether the change is acceptable for display based on the determination of the presence or absence of one or more rule violations.

[0142] In one embodiment, a method executed by a computer includes means for receiving image data regarding a patient's organ. The method also includes means for determining a target region recommended as a treatment target for the organ based on the image data. Further, the method includes means for generating recommended target data characterizing the recommended target region of the organ. The method also includes means for storing the recommended target data in a database.

[0143] In one embodiment, a method executed by a computer includes means for receiving a first input for specifying a change to the target region recommended as a treatment target. The method also includes means for determining whether the change violates a first rule based on the change to the target region recommended as a treatment target. Further, the method includes means for providing an indication of whether the change is acceptable for display based on the determination of the presence or absence of one or more rule violations.

[0144] In one embodiment, a method executed by a computer includes means for receiving image data regarding a patient. The method also includes means for determining a scar position of an organ based on the image data. Further, the method includes means for determining any one of a plurality of segments of a model of the organ based on the scar position. The method also includes means for displaying the model in which the determined segment is identified. In one embodiment, the method includes means for overlaying the image data to display the model. In one embodiment, the method includes means for overlaying the model to display the image data.

[0145] In one embodiment, a method executed by a computer includes means for receiving image data regarding a patient. The method includes means for determining a scar position of an organ based on the image data. Further, the method includes means for determining a healthy portion of the organ based on the scar position. The method also includes means for displaying a model of the organ in which the scar position and the healthy portion are identified.

[0146] The method described above refers to the illustrated flowchart. Of course, many other methods for performing operations related to the method can be used. For example, it may be possible to change the order of processing, and some of the described processing may be optional.

[0147] Furthermore, the methods and systems described herein can be embodied at least in part in a computer-executed process and an apparatus for performing that process. Also, the disclosed methods can be embodied at least in part in a tangible, non-transitory machine-readable storage medium encoded with computer program code. For example, each step of the method can be embodied in hardware, in executable instructions (e.g., software) executed by a processor, or in a combination of the two. The medium can include, for example, RAM, ROM, CD-ROM, DVD-ROM, BD-ROM, hard disk drive, flash memory, or other non-transitory machine-readable storage medium. When the computer program code is loaded and executed on a computer, the computer becomes an apparatus for performing the method. Also, the method can be embodied at least in part in a computer on which the computer program code is loaded or executed, where the computer becomes a special-purpose computer for performing the method. When executed on a general-purpose processor, each segment of the computer program code configures the processor to be a dedicated logic circuit. Alternatively, the method can be embodied at least in part in an application-specific integrated circuit for performing the method.

[0148] The foregoing description is provided for purposes of illustration, explanation, and description of embodiments of the present disclosure. Modifications and variations to the embodiments are apparent to those skilled in the art and can be made without departing from the scope and spirit of the present disclosure.

Claims

1. 1. A system including a computing device, The computing device comprises: receiving a first input identifying a change to a target area of ​​treatment; determining whether a first rule is violated based on the change to the target area of ​​the treatment; providing for display an indication of whether the change is acceptable based on a determination of whether one or more rules are violated.

2. The computing device comprises: The system of claim 1 , further configured to update the target region based on the change when it is determined that the first rule is not violated.

3. The computing device comprises: The system of claim 1 , configured, upon determining that the first rule is violated, to provide for display an error message based on the violation.

4. The computing device comprises: The system of claim 1 configured to receive image data, the image data being at least one of magnetic resonance image data and computed tomography image data.

5. The computing device comprises: receiving a second input; generating target data characterizing the target region; The system of claim 1 , configured to transmit the target data to a second computing device for treating a patient.

6. The computing device comprises: configured to display the interactive model in a graphical user interface; The system of claim 1 , wherein the interactive model includes a plurality of segments, and the first input specifies a selection of at least one segment of the plurality of segments.

7. The computing device comprises: The system of claim 6 , configured to display a note associated with the at least one segment of the plurality of segments.

8. The system of claim 6 or 7, wherein the first rule is based on a particular combination of the plurality of segments.

9. The system of claim 6 or 7, wherein the first rule is based on a maximum number of selections of the plurality of segments.

10. The computing device comprises: acquiring image data relating to an organ of a patient in which the target region to be treated is located; generating a segment model based on the organ; The system of claim 1 , configured to display the segment model by overlaying the image data.

11. The computing device comprises: acquiring image data relating to an organ of a patient in which the target region to be treated is located; generating a segment model based on the organ; The system of claim 1 configured to display the image data overlaid with the segment model.

12. The computing device comprises: generating a first digital model of the organ type; determining an alignment of image data with respect to the first digital model; generating a second digital model including at least a portion of the scanned image and the first digital model; The system of claim 1 , configured to store the second digital model in a data repository.

13. The computing device further comprises: The system of claim 12 , configured to provide the second digital model for display.

14. The computing device further comprises: receiving a second input specifying an adjustment to an alignment of the image data and the first digital model; adjusting the second digital model based on the second input; The system of claim 12 or 13, configured to store the adjusted second digital model in the data repository.

15. The computing device comprises: receiving a second input identifying a treatment target region of the organ; determining a corresponding portion of a second digital model based on the treatment target area of ​​the organ; The system of claim 1 , further configured to regenerate the second digital model to identify the corresponding portion.

16. 1. A computer-implemented method comprising: Receiving a first input specifying a change to a target area of ​​treatment; determining whether a first rule is violated based on the change to the target area of ​​the treatment; providing for display an indication of whether the change is acceptable based on a determination of whether one or more rules have been violated.

17. determining that the first rule is not violated; 17. The computer implemented method of claim 16, further comprising updating the target region based on the changes.

18. determining that the first rule is violated; 17. The computer implemented method of claim 16, comprising providing an error message for display based on the violation.

19. 1. A non-transitory computer-readable medium having instructions recorded thereon that, when executed by at least one processor, cause the at least one processor to perform a process, comprising: The process comprises: Receiving a first input specifying a change to a target area of ​​treatment; determining whether a first rule is violated based on the change to the target area of ​​the treatment; and providing for display an indication of whether the change is acceptable based on a determination of whether one or more rules are violated.

20. The process further comprises: determining that the first rule is not violated and updating the target region based on the change; or determining that the first rule is violated and, based on the violation, providing an error message for display; 20. The non-transitory computer-readable medium of claim 19, comprising at least one of:

Images